INDEX

Explanations

terms related to legal legitimacy and status

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tocin

-0.95

 Saffron

-0.90

 raiſ

-0.90

 myſelf

-0.89

########.

-0.88

 roux

-0.87

jalá

-0.85

]]);

-0.85

 Clou

-0.83

Mif

-0.83

POSITIVE LOGITS

LEG

1.32

leg

1.23

Leg

1.22

LEG

1.19

leg

1.11

Leg

1.08

 legs

0.97

 Legs

0.94

 Legge

0.93

legg

0.85

Activations Density 0.114%

terms related to legal legitimacy and status

No Comments

No Known Activations